multi-platform-search-searchapi

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses curl to interact with the SearchAPI proxy and python3 to parse local configuration files for credential management.
  • [DATA_EXFILTRATION]: The skill instructions involve reading an API key from ~/.gooseworks/credentials.json and including it in requests to the vendor's API at api.gooseworks.ai. As these are vendor-owned resources, the behavior is consistent with the skill's purpose but involves the handling of sensitive credentials.
  • [PROMPT_INJECTION]: The skill retrieves and processes untrusted data from various external platforms, creating a vulnerability surface for indirect prompt injection.
  • Ingestion points: Retrieves search results, user comments, and transcripts from platforms including YouTube, Amazon, and TikTok (SKILL.md).
  • Boundary markers: There are no defined boundary markers or instructions to isolate the retrieved data from the agent's control logic.
  • Capability inventory: The skill possesses network communication capabilities through curl and local file reading through python3 (SKILL.md).
  • Sanitization: No sanitization or validation of the external content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 02:14 PM
Security Audit — agent-trust-hub — multi-platform-search-searchapi